ROW-SLAM: Under-Canopy Cornfield Semantic SLAM
This addresses the challenge of precise robot navigation for agricultural tasks like weeding, but it is incremental as it adapts existing SLAM methods to a specific domain.
The paper tackles the problem of autonomous weeding in cornfields by developing a semantic SLAM system to detect and localize corn stalks under the canopy, achieving robust results in field trials across various conditions.
We study a semantic SLAM problem faced by a robot tasked with autonomous weeding under the corn canopy. The goal is to detect corn stalks and localize them in a global coordinate frame. This is a challenging setup for existing algorithms because there is very little space between the camera and the plants, and the camera motion is primarily restricted to be along the row. To overcome these challenges, we present a multi-camera system where a side camera (facing the plants) is used for detection whereas front and back cameras are used for motion estimation. Next, we show how semantic features in the environment (corn stalks, ground, and crop planes) can be used to develop a robust semantic SLAM solution and present results from field trials performed throughout the growing season across various cornfields.